【摘要】：在實(shí)際生活中,大型建筑結(jié)構(gòu)和設(shè)備在服役過程中會(huì)或多或少的出現(xiàn)損傷問題,如果沒有被及時(shí)發(fā)現(xiàn)和處理,往往會(huì)造成人財(cái)兩盡的嚴(yán)重后果,所以結(jié)構(gòu)的健康監(jiān)測(cè)、診斷、評(píng)估和預(yù)測(cè)顯得尤為重要。本文在結(jié)構(gòu)健康監(jiān)測(cè)的前提下,以結(jié)構(gòu)健康狀態(tài)趨勢(shì)預(yù)測(cè)為目的,進(jìn)行結(jié)構(gòu)損傷特征的分析與提取,研究結(jié)構(gòu)的損傷趨勢(shì)。具體的研究?jī)?nèi)容如下:研究了基于經(jīng)驗(yàn)小波變換(Empirical Wavelet Transform,簡(jiǎn)稱EWT)的信號(hào)預(yù)處理方法,利用EWT對(duì)采集的結(jié)構(gòu)損傷加速度振動(dòng)信號(hào)的頻譜進(jìn)行自適應(yīng)分割,構(gòu)造出合適且正交的小波帶通濾波器組,得到具有緊支撐傅里葉頻譜的調(diào)幅-調(diào)頻(Amplitude Modulated-Frequency Modulated,簡(jiǎn)稱AM-FM)分量,再提取出包含豐富損傷信息的分量,對(duì)其進(jìn)行Hilbert變換,計(jì)算出瞬時(shí)頻率和瞬時(shí)幅值。實(shí)驗(yàn)結(jié)果表明:瞬時(shí)頻率能夠反映出結(jié)構(gòu)發(fā)生損傷前后的剛度變化形式,而且檢測(cè)節(jié)點(diǎn)位置不同或者損傷工況不同其瞬時(shí)頻率都會(huì)有明顯的差異,故將其作為結(jié)構(gòu)健康狀態(tài)的預(yù)測(cè)指標(biāo),可以很好地反映結(jié)構(gòu)健康狀態(tài)的變化趨勢(shì),為進(jìn)一步的損傷趨勢(shì)預(yù)測(cè)奠定了基礎(chǔ)。研究了模糊理論和回聲狀態(tài)網(wǎng)絡(luò)相結(jié)合的非線性時(shí)間序列預(yù)測(cè)方法,對(duì)其推理算法、訓(xùn)練過程和網(wǎng)絡(luò)的關(guān)鍵參數(shù)進(jìn)行了詳細(xì)地研究說明,并對(duì)該網(wǎng)絡(luò)算法的穩(wěn)定性能進(jìn)行嚴(yán)格的定義。實(shí)驗(yàn)結(jié)果表明:選取合適的參數(shù)對(duì)預(yù)測(cè)精度有一定影響,采用雙曲正切(tanh)型神經(jīng)元激活函數(shù)的預(yù)測(cè)精度比泄露(leaky)型更高,相比于傳統(tǒng)的回聲狀態(tài)網(wǎng)絡(luò),模糊回聲狀態(tài)網(wǎng)絡(luò)(Fuzzy Echo State Network,簡(jiǎn)稱FESN)的非線性逼近能力強(qiáng),預(yù)測(cè)精度高且能夠處理較大的樣本數(shù)據(jù),訓(xùn)練效率也有一定的提高,為實(shí)際工程結(jié)構(gòu)的健康狀態(tài)預(yù)測(cè)提供了理論依據(jù)。研究了基于FESN的結(jié)構(gòu)健康狀態(tài)趨勢(shì)預(yù)測(cè)方法,應(yīng)用EWT方法提取出結(jié)構(gòu)內(nèi)部具有損傷信息的AM-FM分量,并進(jìn)行Hlibert變換,得到瞬時(shí)頻率,再將其作為預(yù)測(cè)模型的輸入。應(yīng)用FESN分別對(duì)單自由度結(jié)構(gòu)和多自由度結(jié)構(gòu)模型進(jìn)行工程仿真預(yù)測(cè),并應(yīng)用于實(shí)際工程數(shù)據(jù)的預(yù)測(cè)。實(shí)驗(yàn)結(jié)果表明:FESN預(yù)測(cè)模型更加逼近真實(shí)值,預(yù)測(cè)精度更高。
[Abstract]:In real life, large building structures and equipment will be damaged more or less in the course of service. If they are not detected and dealt with in time, they will often result in serious consequences for both human and financial resources. Therefore, structural health monitoring and diagnosis, Evaluation and prediction are particularly important. On the premise of structural health monitoring, this paper analyzes and extracts the structural damage characteristics and studies the damage trend of the structure in order to predict the trend of structural health state. The specific research contents are as follows: the signal preprocessing method based on empirical wavelet transform (Empirical Wavelet Transform,) is studied, and the spectrum of structural damage acceleration vibration signal collected by EWT is segmented adaptively by EWT. An appropriate and orthogonal wavelet bandpass filter bank is constructed to obtain the amplitude modulation-frequency modulation (AM-FM) component with compact support Fourier spectrum, and then extract the component which contains abundant damage information, and then carry on the Hilbert transform to it. The instantaneous frequency and amplitude are calculated. The experimental results show that the instantaneous frequency can reflect the stiffness change of the structure before and after the damage, and the instantaneous frequency will be obviously different with the different location of the detection node or the different damage condition. Therefore, taking it as a predictor of structural health state can well reflect the changing trend of structural health state and lay a foundation for further prediction of damage trend. The nonlinear time series prediction method based on fuzzy theory and echo state network is studied. The reasoning algorithm, the training process and the key parameters of the network are studied in detail. And the stability of the network algorithm is strictly defined. The experimental results show that choosing appropriate parameters has certain influence on the prediction accuracy. The prediction accuracy of hyperbolic tangent (tanh) neuron activation function is higher than that of leaking (leaky) type, compared with the traditional echo state network. Fuzzy echo state network (Fuzzy Echo State Network,) has strong nonlinear approximation ability, high prediction accuracy and ability to deal with large sample data, and the training efficiency is also improved to a certain extent. It provides a theoretical basis for the prediction of the health state of practical engineering structures. In this paper, the structure health trend prediction method based on FESN is studied. The AM-FM component with damage information is extracted by EWT method, and the instantaneous frequency is obtained by Hlibert transform, which is used as the input of the prediction model. The single degree of freedom structure and multi-degree-of-freedom structure model are simulated by FESN and applied to the prediction of practical engineering data. The experimental results show that the FESN prediction model is more close to the real value and the prediction accuracy is higher.
【學(xué)位授予單位】：長(zhǎng)安大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TU317

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 喬俊飛;李瑞祥;柴偉;韓紅桂;;基于PSO-ESN神經(jīng)網(wǎng)絡(luò)的污水BOD預(yù)測(cè)[J];控制工程;2016年04期

2 黃南天;張書鑫;蔡國(guó)偉;徐殿國(guó);;采用EWT和OCSVM的高壓斷路器機(jī)械故障診斷[J];儀器儀表學(xué)報(bào);2015年12期

3 馮博;李輝;鄭海起;;基于經(jīng)驗(yàn)小波變換的軸承故障診斷研究[J];軸承;2015年12期

4 姚顯雙;倫淑嫻;;基于回聲狀態(tài)網(wǎng)的光伏發(fā)電量預(yù)測(cè)[J];電子設(shè)計(jì)工程;2015年22期

5 林健;倫淑嫻;;基于改進(jìn)回聲狀態(tài)網(wǎng)的時(shí)間序列預(yù)測(cè)[J];渤海大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年03期

6 楊斌;程軍圣;;基于自適應(yīng)最稀疏時(shí)頻分析的結(jié)構(gòu)損傷檢測(cè)方法[J];振動(dòng)工程學(xué)報(bào);2015年04期

7 田中大;高憲文;李樹江;王艷紅;;遺傳算法優(yōu)化回聲狀態(tài)網(wǎng)絡(luò)的網(wǎng)絡(luò)流量預(yù)測(cè)[J];計(jì)算機(jī)研究與發(fā)展;2015年05期

8 李志農(nóng);朱明;褚福磊;肖堯先;;基于經(jīng)驗(yàn)小波變換的機(jī)械故障診斷方法研究[J];儀器儀表學(xué)報(bào);2014年11期

9 崔建國(guó);王青天;滑嬌嬌;樸春雨;齊義文;蔣麗英;;基于DMS和LS-SVM的復(fù)合材料結(jié)構(gòu)健康預(yù)測(cè)方法[J];材料導(dǎo)報(bào);2014年16期

10 謝宗蕻;劉海涵;張子龍;;層間增韌復(fù)合材料層合板低速?zèng)_擊損傷預(yù)測(cè)[J];南京航空航天大學(xué)學(xué)報(bào);2013年05期

相關(guān)博士學(xué)位論文 前3條

1 楊飛;基于回聲狀態(tài)網(wǎng)絡(luò)的交通流預(yù)測(cè)模型及其相關(guān)研究[D];北京郵電大學(xué);2012年

2 王建民;基于回聲狀態(tài)網(wǎng)絡(luò)的非線性時(shí)間序列預(yù)測(cè)方法研究[D];哈爾濱工業(yè)大學(xué);2011年

3 劉義艷;結(jié)構(gòu)健康監(jiān)測(cè)與智能診斷技術(shù)研究[D];長(zhǎng)安大學(xué);2010年

相關(guān)碩士學(xué)位論文 前2條

1 齊紅云;基于模糊雙曲正切模型的回聲狀態(tài)網(wǎng)改進(jìn)及其應(yīng)用研究[D];渤海大學(xué);2016年

2 范廣露;基于回聲狀態(tài)網(wǎng)絡(luò)的設(shè)備健康狀態(tài)監(jiān)測(cè)與預(yù)測(cè)方法[D];長(zhǎng)安大學(xué);2012年

，

本文編號(hào)：2396119